Towards Sharper Utility Bounds for Differentially Private Pairwise Learning
Not on the map. Why?
Abstract (arXiv)
Pairwise learning focuses on learning tasks with pairwise loss functions, depends on pairs of training instances, and naturally fits for modeling relationships between pairs of samples. In this paper, we focus on the privacy of pairwise learning and propose a new differential privacy paradigm for pairwise learning, based on gradient perturbation. Except for the privacy guarantees, we also analyze the excess population risk and give corresponding bounds under both expectation and high probability conditions. We use the textiton-average stability and the textitpairwise locally elastic stability theories to analyze the expectation bound and the high probability bound, respectively. Moreover, our analyzed utility bounds do not require convex pairwise loss functions, which means that our method is general to both convex and non-convex conditions. Under these circumstances, the utility bounds are similar to (or better than) previous bounds under convexity or strongly convexity assumption, which are attractive results.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 12 of its 30 references that are in the map. First posted on arXiv 7 May 2021.
Builds on
12 of 30 references.
References · 12
- 2016Deep Learning with Differential Privacycited by 2,682
- 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
- 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
- 2016Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Lojasiewicz Conditioncited by 526
- 2017Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysiscited by 242
- 2018Differentially Private Empirical Risk Minimization Revisited: Faster and More Generalcited by 127
- 2017Efficient Private ERM for Smooth Objectivescited by 61
- 2013A Survey on Metric Learning for Feature Vectors and Structured Datacited by 57
- 2019Stochastic Gradient Descent for Nonconvex Learning without Bounded Gradient Assumptionscited by 48
- 2020Toward Better Generalization Bounds with Locally Elastic Stabilitycited by 41
- 2017Algorithmic stability and hypothesis complexitycited by 39
- 2020A Classification-Based Approach to Semi-Supervised Clustering with Pairwise Constraintscited by 10
Built on by
Citing papers per year: 2023: 2.
2 papers.